xfyun-image-understanding

Community

Describe images with iFlytek Spark Vision.

AuthorJaykaijack
Version1.0.0
Installs0

System Documentation

What problem does it solve?

iFlytek Spark Vision-based image understanding enables automated description of visual content and answering questions about images via a WebSocket API, using pure Python stdlib without pip dependencies.

Core Features & Use Cases

  • Describe an image: Generate natural-language descriptions of visual scenes from a given image file.
  • Ask a question about an image: Interactively query objects, scenes, or details in the image and receive targeted responses.
  • Pure stdlib WebSocket client: Demonstrates a dependency-free client using only Python's standard library for WebSocket communication.
  • Setup & credentials: Requires environment variables XFYUN_APP_ID, XFYUN_API_KEY, and XFYUN_API_SECRET.

Quick Start

Run python3 scripts/image_understanding.py photo.jpg to describe the image, and use -q to ask a question about it.

Dependency Matrix

Required Modules

None required

Components

scripts

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: xfyun-image-understanding
Download link: https://github.com/Jaykaijack/openclaw-backup/archive/main.zip#xfyun-image-understanding

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.